9 days ago - req22940
Machine Learning Internship: Machine Learning for SEM image processing
Research & development
Computer science & software engineering
In a nutshell
Research & development
No experience (Student)
Computer science & software engineering, Data science, Mathematics
Are you a Master student with project experience in Machine Learning? Are you well versed in Python and do you have an interest in SEM images? Then this assignment in our Research department could be of your interest!
An essential aspect in the production of semiconductor wafers is the verification that the printed patterns on those wafers are within specification. This requires ‘Critical Dimension’ (CD) metrology of these patterns: measuring the widths of lines and diameters of contact holes using a ‘Scanning Electron Microscope’ (SEM). Due to the ever shrinking pattern size, we enter the regime in which the SEM measurement itself starts to influence the measured quantities. Electron beam-induced charging of the wafer surface affects the trajectories of the secondary electrons, leading to inaccurate CD metrology.
Physical models are able to reproduce charging artefacts that we see in experimental images. We believe that these models can be used to train a deep learning model, that could eliminate charging artefacts from experimental images and increase the accuracy of the CD-measurement. Your assignment will be to develop and test this approach. Specifically, we expect you to
• Set up deep neural network with an encoder-decoder (U-net, ResNet, etc.) architecture.
• Train the network using simulated SEM images with varying geometries and charging artefacts.
• Validate the model by applying the network to an independent set of simulated SEM images.
• Validate the model by applying the network to experimental images. Quantify the performance of CD measurement before and after applying the network.
You are a Master student in the field of Applied Mathematics, Physics, Electrical engineering, Computer Science or Data Sciece. Familiarity with machine learning and its implementation is critical for this assignment. You should be well versed in Python (including knowledge of some of the deep learning frameworks such as PyTorch, Keras, Tensorflow), and be interested to learn how SEM images are used in the semiconductor industry. You are naturally curious, self-motivated and good at working independently. You should be comfortable presenting progress on your work on a weekly basis and actively participate in group meeting discussions. Furthermore, your communication skills in English should be excellent.
This is a Master apprentice/graduation internship for 4-5 days a week with duration of 6 months to 1 year. The start date is as soon as possible.
You need to be enrolled as a student at an educational institute during the full length of your internship.
What ASML offers
Your internship will be in one of the leading Dutch corporations, gaining valuable experience in a highly dynamic environment. You will receive a monthly internship allowance based on your educational level and number of days per week, plus a possible housing or travel allowance. More information on the allowances can be found on our website. In addition you will get expert, practical guidance and the chance to work in and experience a dynamic, innovative team environment.
ASML: Be part of progress
We make machines that make chips – the hearts of the devices that keep us informed, entertained and safe; that improve our quality of life and help to tackle the world’s toughest problems.
We build some of the most amazing machines that you will ever see, and the applications to run them. Never satisfied, we measure our performance in units that begin with pico or nano.
We believe we can always do better. We believe the winning idea can come from anyone. We love what we do – not because it’s easy, but because it’s hard. At ASML we are always pushing technology further.
Students: Getting ready for the real-world
Teamwork is key within ASML. Our R&D team is more than 5,500 people strong and worldwide we form one big team with over 25,000 employees. These colleagues have 123 different nationalities and work at our major sites on three continents.
Dozens of diverse, interdisciplinary teams work in parallel to meet a challenging development schedule. In this inspiring environment, your colleagues may be sitting next door, or they could be thousands of kilometers away in a different country, or even working for a different company.
An internship at ASML is your opportunity to get to know this world and get a feel for that excites you most. Use your education, gain real-life working experience and explore the world of high-tech – all at the same time.
How will you be part of progress?